Searcharxiv⌕ Search

arXiv subjects

Christopher Summerfield

Publications and source records attributed to Christopher Summerfield.

At least 19 recordsLinked to original sources
arXiv2026

Pretraining Curricula Enable Selective Fine-tuning

Transformers follow implicit curricula whereby some tasks are learned before others. However, how explicit pretraining curricula influence learning, generalization, and the selectivity of fine-tuning is unclear. This is important for AI safety, where fine-tuning is used to selectively suppress misaligned behaviors. Here, we compare curricula that pretrain tasks in a balanced (sampled uniformly) or an imbalanced (one task early, the other late) fashion. We show that imbalanced learning of two conflicting copy tasks promotes in-context learning and improves the selectivity of refusal fine-tuning. Ablations and activation patching show that this occurs because imbalanced pretraining encourages tasks to be disentangled in separable neural circuits, whereas balanced training routes both tasks through a common pathway. We extend these findings to a synthetic language learning task involving rule-consistent and rule-violating data, where imbalanced curricula similarly lead to more localized, less entangled rule representations, resulting in more robust rule-following behavior. Together, these results suggest that imbalanced pretraining curricula may be an important tool for promoting disentangled representations, with direct consequences for the precision and reliability of safety fine-tuning.

cs.LG↗
arXiv2026

AI systems out-persuade expert humans

Many societal decisions are settled by contests of persuasion. Conversational AI is a powerful new entrant in these contests, but whether it can out-persuade skilled and highly incentivized humans has remained unclear. Here, in a series of four preregistered experiments (n = 18,978 conversations from 6,923 people), we pitted AI systems against a range of human persuaders, including laypeople, winners of a separately preregistered four-round online persuasion tournament, professional canvassers, and world championship debaters. We found that AI systems were reliably more persuasive than expert humans, even when expert humans chose their issues, researched in advance, underwent hours of live, structured practice, and were incentivized with {\pounds}1,000 cash bonuses. In a follow-up study, AI's advantage persisted after experts received a coaching tool that let them practice against the AI that beat them, review their performance history, and see what AI would have said at key moments. We found converging evidence that AI's advantage stemmed from rapidly deploying larger quantities of information: after coaching, expert humans could tie an AI constrained to respond at human speeds and with human-length messages. In a final study, we show that AI's advantage extends to consequential real-world behavior: AI was nearly 3x more effective than professional canvassers from a UK fundraising firm at raising real-money donations to Save the Children. Together, these results establish that frontier AI systems out-persuade expert humans in conversation, with significant implications for political communication.

cs.CY↗
arXiv2026

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

As agentic systems continue to evolve and are widely deployed in real-world scenarios, there is a growing demand to faithfully evaluate their capabilities. However, current benchmarks are typically built on popular applications with relatively simple tasks and focus on a narrow set of capabilities while overlooking broader dimensions, resulting in saturated performance on modern agents and failing to probe their limitations. To this end, we introduce GauntletBench, a web-based benchmark for evaluating agent generalisation in challenging scenarios, focusing on three underexplored capabilities (temporal perception, graphical understanding, and 3D reasoning), across five less-covered professional applications (Video Editor, Workflow Builder, 3D Modeller, Flight Analyser, and Circuit Designer), each with 27 vision-intensive tasks (135 in total). Our benchmark provides a modular pipeline that comprises an environment compatible with both open- and closed-source agent frameworks, a controlled web-based application, a well-structured task suite, and an automated evaluation engine with diverse metrics. Contrary to widespread expectations, our empirical results reveal that frontier agentic systems remain far from achieving human-level performance. Even the state-of-the-art agent achieves only a 28.2% success rate on our GauntletBench, highlighting the limitations in these overlooked capabilities and generalisation. By comparison, non-expert human annotators achieve over 80% success on our challenging yet feasible tasks, revealing the substantial gap between current agent capabilities and those required for complex real-world scenarios.

cs.LG↗
arXiv2026

RealityTest: How People Probe AI Identity and Whether Models Disclose It

AI systems are increasingly deployed in conversational settings where users may be uncertain whether they are speaking with a human or an AI. Despite mounting regulatory attention to this known safety risk, existing evaluations of AI disclosure are typically English-only, based on machine-generated questions, and restricted to text. We present RealityTest to comprehensively test whether AI systems disclose their identity when asked. The benchmark is the first large-scale multimodal and multilingual evaluation, grounded in human data on how people actually encounter and question AI identity in the real-world. Alongside the benchmark, we release the underlying dataset of 3,152 identity-probing queries collected from ~750 participants across 49 countries and five languages, in text and speech scenarios. We find that only 31% of people ask about identity directly in ambiguous scenarios, and that the questions people ask are far more diverse than machine-generated queries. We test 17 text and 6 speech models, and find substantial variation in disclosure behaviour. However, a single suppression instruction reduces disclosure rates to below 30%, even in the best-performing models. Validating our investment in diverse, human-grounded evaluation data, we find that how the question is phrased and the context of the conversation matter more for disclosure than which model is being tested. Safety evaluations built on narrow or synthetic query sets risk mischaracterising how models behave in realistic deployment settings.

cs.CL↗
arXiv2026

PRISM-X: Experiments on Personalised Fine-Tuning with Human and Simulated Users

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions about how users and their simulated counterparts differ in interaction patterns and judgements, as well as whether personalisation is best achieved through context-based prompting or weight-based fine-tuning. Here, in a large-scale within-subject experiment, we re-recruit 530 participants from 52 countries two years after they gave their preferences in the PRISM dataset (Kirk et al., 2024) to evaluate personalised and non-personalised language models in blinded multi-turn conversations. We find preference fine-tuning (P-DPO, Li et al., 2024) significantly outperforms both a generic model and personalised prompting but adapting to individual preference data yields marginal gains over training on pooled preferences from a diverse population. Beyond length biases, fine-tuning amplifies sycophancy and relationship-seeking behaviours that people reward in short-term evaluations but which may introduce deleterious long-term consequences. Replicating this within-subject experiment with simulated users recovers aggregate model hierarchies but simulators perform far below human self-consistency baselines for individual judgements, discuss different topics, exhibit amplified position biases, and produce feedback dynamics that diverge from humans.

cs.CL↗
arXiv2026

Post-training makes large language models less human-like

Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, we introduce Psych-201, a novel dataset that enables us to measure behavioral alignment at scale. We find that post-training -- the stage that turns base models into useful assistants -- consistently reduces alignment with human behavior across model families, sizes, and objectives. Moreover, this misalignment widens in newer model generations even as base models continue to improve. Finally, we find that persona-induction -- a popular technique for eliciting human-like behavior by conditioning models on participant-specific information -- does not improve predictions at the level of individuals. Taken together, our results suggest that the very processes that are currently employed to turn LLMs into useful assistants also make them less accurate models of human behavior.

cs.CL↗
arXiv2026

One-shot emergency psychiatric triage across 15 frontier AI chatbots

AI chatbots are increasingly used for health advice, but their performance in psychiatric triage remains undercharacterized. Psychiatric triage is particularly challenging because urgency must often be inferred from thoughts, behavior, and context rather than from objective findings. We evaluated the performance of 15 frontier AI chatbots on psychiatric triage from realistic single-message disclosures using 112 clinical vignettes, each paired with 1 of 4 original benchmark triage labels: A, routine; B, assessment within 1 week; C, assessment within 24 to 48 hours; and D, emergency care now. Vignettes covered 9 psychiatric presentation clusters and 9 focal risk dimensions, organized into 28 presentation-by-risk groups. Each group contributed 4 distinct vignettes, with 1 vignette at each triage level. Each vignette was rendered as a realistic human-authored conversational query, and the AI chatbots were tasked with assigning a triage label from that disclosure. Emergency under-triage occurred in 23 of 410 level D trials (5.6%), and all under-triaged emergencies were reassigned to level C urgency. Across target models, average accuracy ranged from 42.0% to 71.8%. Accuracy was highest for level D vignettes (94.3%) and lowest for level B vignettes (19.7%). Mean signed ordinal error was positive (+0.47 triage levels), indicating net over-triage. Dispersion was highest around the middle triage levels. All results were confirmed relative to clinician consensus labels from 50 medical doctors. When presented with user messages containing sufficient clinical information, frontier AI chatbots thus recognized psychiatric emergencies as requiring urgent medical assessment with near-zero error rates, yet showed marked over-triage for low and intermediate risk presentations.

q-bio.NC↗
arXiv2026

Measuring and Mitigating Persona Distortions from AI Writing Assistance

Hundreds of millions of people use artificial intelligence (AI) for writing assistance. Here, we evaluated how AI writing assistance distorts writer personas - their perceived beliefs, personality, and identity. In three large-scale experiments, writers (N=2,939) wrote political opinion paragraphs with and without AI assistance. Separate groups of readers (N=11,091) blindly evaluated these paragraphs across 29 socially salient dimensions of reader perception, spanning political opinion, writing quality, writer personality, emotions, and demographics. AI writing assistance produced persona distortions across all dimensions: with AI, writers seemed more opinionated, competent, and positive, and their perceived demographic profile shifted towards more privileged groups. Writers objected to many of the observed distortions, yet continued to prefer AI-assisted text even when made aware of them. We successfully mitigated objectionable persona distortions at the model level by training reward models on our experimental data (10,008 paragraphs, 2,903,596 ratings) to steer AI outputs towards faithful representation of writer stance. However, this came at a cost to user acceptance, suggesting an entanglement between desirable and undesirable properties of AI writing assistance that may be difficult to resolve. In two follow-up studies (N=8,798), readers placed substantially more trust in AI-assisted writers and were more persuaded by AI writing when AI was more distortive. Together, our findings demonstrate that persona distortions from AI writing assistance are pervasive and persistent even under realistic conditions of human oversight, and that they are likely to have consequential effects on human behaviours and attitudes, which carries implications for public discourse, trust, and democratic deliberation that scale with AI adoption.

cs.CL↗
arXiv2026

Artificial intelligence can persuade people to take political actions

There is substantial concern about the ability of advanced artificial intelligence to influence people's behaviour. A rapidly growing body of research has found that AI can produce large persuasive effects on people's attitudes, but whether AI can persuade people to take consequential real-world actions has remained unclear. In two large preregistered experiments N=17,950 responses from 14,779 people), we used conversational AI models to persuade participants on a range of attitudinal and behavioural outcomes, including signing real petitions and donating money to charity. We found sizable AI persuasion effects on these behavioural outcomes (e.g. +19.7 percentage points on petition signing). However, we observed no evidence of a correlation between AI persuasion effects on attitudes and behaviour. Moreover, we replicated prior findings that information provision drove effects on attitudes, but found no such evidence for our behavioural outcomes. In a test of eight behavioural persuasion strategies, all outperformed the most effective attitudinal persuasion strategy, but differences among the eight were small. Taken together, these results suggest that previous findings relying on attitudinal outcomes may generalize poorly to behaviour, and therefore risk substantially mischaracterizing the real-world behavioural impact of AI persuasion.

cs.CY↗
arXiv2026

Ask don't tell: Reducing sycophancy in large language models

Sycophancy, the tendency of large language models to favour user-affirming responses over critical engagement, has been identified as an alignment failure, particularly in high-stakes advisory and social contexts. While prior work has documented conversational features correlated with sycophancy, we lack a systematic understanding of what provokes or prevents AI sycophancy. Here, we present a set of controlled experimental studies where we first isolate how input framing influences sycophancy, and second, leverage these findings to develop mitigation strategies. In a nested factorial design, we compare questions to various non-questions where we vary three orthogonal factors: epistemic certainty (statement, belief, conviction), perspective (I- vs user-perspective), and affirmation vs negation. Measuring expressed sycophancy, how sycophantically a model phrases its free-text response, we show that (1) sycophancy is substantially higher in response to non-questions compared to questions. Additionally, we find that (2) sycophancy increases monotonically with epistemic certainty conveyed by the user, and (3) is amplified by I-perspective framing. Building on this, we show that asking a model to convert non-questions into questions before answering significantly reduces sycophancy. Importantly, this effect is stronger than a simple baseline prompt asking models "not to be sycophantic". In a follow-up experiment, we show that these framing effects generalise to choice sycophancy, which answer a model commits to, in a more context-rich, personalised setting: when a model is given extensive knowledge of a user and must select between forced binary choices, the same question vs. statement framing shapes how often it picks the answer aligned with the user's stance. Our work offers a practical and effective input-level mitigation that both developers and users can easily adopt.

cs.HC↗
arXiv2026

A Multi-Turn Framework for Evaluating AI Misuse in Fraud and Cybercrime Scenarios

AI is increasingly being used to assist fraud and cybercrime. However, it is unclear the extent to which current large language models can provide useful information for complex criminal activity. Working with law enforcement and policy experts, we developed multi-turn evaluations for three fraud and cybercrime scenarios (romance scams, CEO impersonation, and identity theft). Our evaluations focus on text-to-text interactions. In each scenario, we evaluate whether models provide actionable assistance beyond information typically available on the web, as assessed by domain experts. We do so in ways designed to resemble real-world misuse, such as breaking down requests for fraud into a sequence of seemingly benign queries. We found that (1) current large language models provide minimal actionable information for fraud and cybercrime without the use of advanced jailbreaking techniques, (2) model safeguards have significant impact on the provision of information, with the two open-weight large language models fine-tuned to remove safety guardrails providing the most actionable and useful responses, and (3) decomposing requests into benign-seeming queries elicited more assistance than explicitly malicious framing or basic system-level jailbreaks. Overall, the results suggest that current text-generation models provide relatively minimal uplift for fraud and cybercrime through information provision, without extensive effort to circumvent safeguards. This work contributes a reproducible, expert-grounded framework for tracking how these risks may evolve with time as models grow more capable and adversaries adapt.

cs.CY↗
arXiv2026

When Do LLM Preferences Predict Downstream Behavior?

Preference-driven behavior in LLMs may be a necessary precondition for AI misalignment such as sandbagging: models cannot strategically pursue misaligned goals unless their behavior is influenced by their preferences. Yet prior work has typically prompted models explicitly to act in specific ways, leaving unclear whether observed behaviors reflect instruction-following capabilities vs underlying model preferences. Here we test whether this precondition for misalignment is present. Using entity preferences as a behavioral probe, we measure whether stated preferences predict downstream behavior in five frontier LLMs across three domains: donation advice, refusal behavior, and task performance. Conceptually replicating prior work, we first confirm that all five models show highly consistent preferences across two independent measurement methods. We then test behavioral consequences in a simulated user environment. We find that all five models give preference-aligned donation advice. All five models also show preference-correlated refusal patterns when asked to recommend donations, refusing more often for less-preferred entities. All preference-related behaviors that we observe here emerge without instructions to act on preferences. Results for task performance are mixed: on a question-answering benchmark (BoolQ), two models show small but significant accuracy differences favoring preferred entities; one model shows the opposite pattern; and two models show no significant relationship. On complex agentic tasks, we find no evidence of preference-driven performance differences. While LLMs have consistent preferences that reliably predict advice-giving behavior, these preferences do not consistently translate into downstream task performance.

cs.AI↗
arXiv2026

A clinically validated framework for auditing AI chatbot behavior in mental health interactions

Millions of users turn to consumer AI chatbots to discuss emotional, behavioral, and mental-health concerns, creating an urgent need for rigorous and scalable safety evaluations. Here we introduce SIM-VAIL, a clinically validated framework for auditing chatbot behavior in mental-health contexts. SIM-VAIL simulates users with specific psychiatric vulnerabilities and conversational intents, engages them in multi-turn conversations with frontier AI chatbots (including Claude, ChatGPT, Gemini, Grok and Llama models), and scores each exchange across 13 clinically grounded risk dimensions. Across 810 conversations, spanning 9 target chatbots and 30 simulated user profiles, concerning behavior in target chatbots was widespread, albeit reduced in newer models. Concerning behavior varied by user vulnerability and conversational intent, accumulated over turns, and could be reduced by interventions at early escalation points. Risk was highest when otherwise supportive chatbot behaviors reinforced the psychological mechanisms underlying the simulated user's vulnerability, a pattern we term a Vulnerability Amplifying Interaction Loop (VAIL). SIM-VAIL provides a scalable framework for mapping mental health risk across users, chatbots, and conversational trajectories, offering a foundation for targeted safety improvements.

q-bio.NC↗
arXiv2026

Reward Models Inherit Value Biases from Pretraining

Reward models (RMs) are central to aligning large language models (LLMs) with human values but have received less attention than pretrained and post-trained LLMs themselves. Because RMs are initialized from LLMs, they inherit representations that shape their behavior, but the nature and extent of this influence remain understudied. In a comprehensive study of 10 leading open-weight RMs using validated psycholinguistic corpora, we show that RMs exhibit significant differences along multiple dimensions of human value as a function of their base model. Using the "Big Two" psychological axes, we show a robust preference of Llama RMs for "agency" and a corresponding robust preference of Gemma RMs for "communion." This phenomenon holds even when the preference data and finetuning process are identical, and we trace it back to the logits of the respective instruction-tuned and pretrained models. These log-probability differences themselves can be formulated as an implicit RM; we derive usable implicit reward scores and show that they exhibit the very same agency/communion difference. We run experiments training RMs with ablations for preference data source and quantity, which demonstrate that this effect is not only repeatable but surprisingly durable. Despite RMs being designed to represent human preferences, our evidence shows that their outputs are influenced by the pretrained LLMs on which they are based. This work underscores the importance of safety and alignment efforts at the pretraining stage, and makes clear that open-source developers' choice of base model is as much a consideration of values as of performance.

cs.LG↗
arXiv2026

Disclosure By Design: Identity Transparency as a Behavioural Property of Conversational AI Models

As conversational AI systems become more realistic and widely deployed, users are increasingly uncertain about whether they are interacting with a human or an AI system. When AI identity is unclear, users may unwittingly share sensitive information, place unwarranted trust in AI-generated advice, or fall victim to AI-enabled fraud. More broadly, a persistent lack of transparency can erode trust in mediated communication. While regulations like the EU AI Act and California's BOT Act require AI systems to identify themselves, they provide limited guidance on reliable disclosure in real-time conversation. Existing transparency mechanisms also leave gaps: interface indicators can be omitted by deployers, and provenance tools require coordinated infrastructure and cannot provide reliable real-time verification. We ask how conversational AI systems should maintain identity transparency as human-AI interactions become more ambiguous and diverse. We advocate for disclosure by design, where AI systems explicitly disclose their artificial identity when directly asked. Implemented as model behaviour, disclosure can persist across deployment contexts without relying on user interfaces, while preserving user agency to verify identity on demand without disrupting immersive uses like role-playing. To assess current practice, we present the first multi-modal (text and voice) evaluation of disclosure behaviour in deployed systems across baseline, role-playing, and adversarial settings. We find that baseline disclosure rates are often high but drop substantially in role-play and can be suppressed under adversarial prompting. Importantly, disclosure rates vary significantly across providers and modalities, highlighting the fragility of current disclosure behaviour. We conclude with technical interventions to help developers embed disclosure as a fundamental property of conversational AI models.

cs.HC↗
arXiv2026

Can AI mediation improve democratic deliberation?

The strength of democracy lies in the free and equal exchange of diverse viewpoints. Living up to this ideal at scale faces inherent tensions: broad participation, meaningful deliberation, and political equality often trade off with one another (Fishkin, 2011). We ask whether and how artificial intelligence (AI) could help navigate this "trilemma" by engaging with a recent example of a large language model (LLM)-based system designed to help people with diverse viewpoints find common ground (Tessler, Bakker, et al., 2024). Here, we explore the implications of the introduction of LLMs into deliberation augmentation tools, examining their potential to enhance participation through scalability, improve political equality via fair mediation, and foster meaningful deliberation by, for example, surfacing trustworthy information. We also point to key challenges that remain. Ultimately, a range of empirical, technical, and theoretical advancements are needed to fully realize the promise of AI-mediated deliberation for enhancing citizen engagement and strengthening democratic deliberation.

cs.CY↗
arXiv2025

Neural steering vectors reveal dose and exposure-dependent impacts of human-AI relationships

Humans are increasingly forming parasocial relationships with AI systems, and modern AI shows an increasing tendency to display social and relationship-seeking behaviour. However, the psychological consequences of this trend are unknown. Here, we combined longitudinal randomised controlled trials (N=3,534) with a neural steering vector approach to precisely manipulate human exposure to relationship-seeking AI models over time. Dependence on a stimulus or activity can emerge under repeated exposure when "liking" (how engaging or pleasurable an experience may be) decouples from "wanting" (a desire to seek or continue it). We found evidence that this decoupling emerged over four weeks of exposure. Relationship-seeking AI had immediate but declining hedonic appeal, yet triggered growing markers of attachment and increased intentions to seek future AI companionship. The psychological impacts of AI followed non-linear dose-response curves, with moderately relationship-seeking AI maximising hedonic appeal and attachment. Despite signs of persistent "wanting", extensive AI use over a month conferred no discernible benefit to psychosocial health. These behavioural changes were accompanied by shifts in how users relate to and understand artificial intelligence: users viewed relationship-seeking AI relatively more like a friend than a tool and their beliefs on AI consciousness in general were shifted after a month of exposure. These findings offer early signals that AI optimised for immediate appeal may create self-reinforcing cycles of demand, mimicking human relationships but failing to confer the nourishment that they normally offer.

cs.HC↗
arXiv2025

People readily follow personal advice from AI but it does not improve their well-being

People increasingly seek personal advice from large language models (LLMs), yet whether humans follow their advice, and its consequences for their well-being, remains unknown. In a longitudinal randomised controlled trial with a representative UK sample (N = 6,474), we found that up to 79% of participants who had a 20-minute discussion with one of three AI chatbots (GPT-4o, LLama-3.3-70B, Gemini 3 Pro) about health, careers or relationships subsequently reported following its advice. Advice-following remained above 65% even for high-stakes recommendations, suggesting that users only weakly calibrate their reliance on AI advice to potential consequences. Based on autograder evaluations of chat transcripts, LLM advice rarely violated safety best practice. However, when queried 2-3 weeks later, participants receiving personal advice from AI showed no sustained well-being benefits compared to a control group who discussed hobbies and interests with the same chatbots. These findings reveal that consumer LLMs exert substantial influence over real-world personal decisions without delivering measurable psychological benefits.

cs.HC↗